© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25837
    Prev
    Next
    INDEX
    Explanations

    compiler attributes and declarations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on code‐level attribute or annotation markers (e.g. C/C++ attributes like [[…]] or __attribute__((…))).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Abstr
    -0.76
     VIDEOT
    -0.71
     kuni
    -0.71
    而又
    -0.70
    IJ
    -0.69
    ikyuu
    -0.68
    牝
    -0.68
     लेकर
    -0.67
    知的
    -0.66
     impotence
    -0.66
    POSITIVE LOGITS
     inline
    1.64
    inline
    1.23
    ATTRIBUTE
    1.13
     attribute
    1.13
    ATTR
    1.12
    attribute
    1.04
    Inline
    0.99
     Attribute
    0.96
    INLINE
    0.95
     VIS
    0.90
    Activations Density 0.058%

    No Known Activations